Automatic Grading of Disc Herniation, Central Canal Stenosis and Nerve Roots Compression in Lumbar Magnetic Resonance Image Diagnosis.

Aim: Accurate severity grading of lumbar spine disease by magnetic resonance images (MRIs) plays an important role in selecting appropriate treatment for the disease. However, interpreting these complex MRIs is a repetitive and time-consuming workload for clinicians, especially radiologists. Here, we aim to develop a multi-task classification model based on artificial intelligence for automated grading of lumbar disc herniation (LDH), lumbar central canal stenosis (LCCS) and lumbar nerve roots compression (LNRC) at lumbar axial MRIs. Methods: Total 15254 lumbar axial T2W MRIs as the internal dataset obtained from the Fifth Affiliated Hospital of Sun Yat-sen University from January 2015 to May 2019 and 1273 axial T2W MRIs as the external test dataset obtained from the Third Affiliated Hospital of Southern Medical University from June 2016 to December 2017 were analyzed in this retrospective study. Two clinicians annotated and graded all MRIs using the three international classification systems. In agreement, these results served as the reference standard; In disagreement, outcomes were adjudicated by an expert surgeon to establish the reference standard. The internal dataset was randomly split into an internal training set (70%), validation set (15%) and test set (15%). The multi-task classification model based on ResNet-50 consists of a backbone network for feature extraction and three fully-connected (FC) networks for classification and performs the classification tasks of LDH, LCCS, and LNRC at lumbar MRIs. Precision, accuracy, sensitivity, specificity, F1 scores, confusion matrices, receiver-operating characteristics and interrater agreement (Gwet k) were utilized to assess the model's performance on the internal test dataset and external test datasets. Results: A total of 1115 patients, including 1015 patients from the internal dataset and 100 patients from the external test dataset [mean age, 49 years ± 15 (standard deviation); 543 women], were evaluated in this study. The overall accuracies of grading for LDH, LCCS and LNRC were 84.17% (74.16%), 86.99% (79.65%) and 81.21% (74.16%) respectively on the internal (external) test dataset. Internal and external testing of three spinal diseases showed substantial to the almost perfect agreement (k, 0.67 - 0.85) for the multi-task classification model. Conclusion: The multi-task classification model has achieved promising performance in the automated grading of LDH, LCCS and LNRC at lumbar axial T2W MRIs.

[Blood-lipid levels of 20 041 kindergarten children aged 3 to 6 in Tianjin].

OBJECTIVE: To understand the level of blood-lipid and prevalence of dyslipidemia of children aged 3 to 6 in Tianjin, so as to provide evidence for large-scale blood screening strategy and to develop intervention of dyslipidemia and cardiovascular in children. METHODS: 20,041 children aged 3 to 6 from 48 kindergartens were involved in this study, in Tianjin. Peripheral blood was collected from right leech-finger of these children, after fatless breakfast. Total cholesterol (TC) and triglyceride (TG) of plasma were tested using Toshiba 120 Automatic Biochemical Analyzer. RESULTS: The average levels of TC and TG were (4.17±0.69) mmol/L and (0.86±0.44) mmol/L in these children. 11.4% of the children had either TC or TG dyslipidemia, with 7.1% had only TC dyslipidemia, 4.9% had only TG dyslipidemia, and 0.6% of them had both TC and TG dyslipidemia. The prevalence of TC dyslipidemia was significantly higher among girls than boys. The prevalence rates of TC dyslipidemia and TG dyslipidemia were different among age groups, but with no significant changes among age groups. The prevalence of TG dyslipidemia was significantly different, with obese children higher than those with normal or overweight children. Different residential areas seemed to be related to the difference on the prevalence of dyslipidemia. Prevalence of TC dyslipidemia was higher in urban than in rural areas. Prevalence of TG dyslipidemia was higher in rural than urban areas. CONCLUSION: The prevalence of dyslipidemia for children aged 3 to 6 was high in Tianjin, and showed differences among genders, age groups and residential regions. Screening and intervention programs on dyslipidemia should be undertaken routinely in children, in order to prevent adult atherosclerosis and coronary heart disease.

Submucous colon lipoma: a case report and review of the literature.

Colon lipoma is remarkably rare in clinical practice. We reported a case of ascending colon lipoma in an 83-year-old woman. She was asymptomatic with a lipoma of 35 mm x 30 mm x 24 mm in size which was found by routine colonoscopy. Right hemicolectomy was performed uneventfully. The diagnosis was made by histological examination. Reviewing the literature and combining with our experience, we discussed the clinical features, diagnosis and treatment of this uncommon disease.